Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrasenewsletter, ratings, nations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     છું
    0.53
     Paperback
    0.53
                                 
    0.52
     Assemble
    0.51
    IllegalArgument
    0.51
     Arjuna
    0.50
     Heron
    0.50
    ▸
    0.50
     Ét
    0.50
     Nada
    0.49
    POSITIVE LOGITS
    wag
    0.48
    his
    0.46
    candles
    0.45
     comerciales
    0.44
    ор
    0.44
    帰
    0.43
    了他的
    0.43
     recibieron
    0.43
    गमेंट
    0.43
    this
    0.42
    Act Density 0.000%

    No Known Activations